© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 23729
    Prev
    Next
    INDEX
    Explanations

    incorrect or wrong

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is strongly triggered by opening parenthesis “(” tokens and the words immediately inside those parentheses.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unpaid
    -0.78
    totalSupply
    -0.72
     Colegio
    -0.72
    拋
    -0.72
    ття
    -0.70
    pheric
    -0.70
    廁
    -0.70
    őség
    -0.69
    ownie
    -0.68
    gbaar
    -0.68
    POSITIVE LOGITS
     wrong
    6.47
     incorrect
    5.69
    wrong
    5.31
    Wrong
    5.06
     Wrong
    4.88
    incorrect
    4.72
     incorrectly
    4.50
     неправи
    4.50
    Incorrect
    4.50
     Incorrect
    4.34
    Activations Density 0.419%

    No Known Activations